© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 53-GEMMASCOPE-2-RES-262K
    7. 37159
    Prev
    Next
    INDEX
    Explanations

    non-negotiable

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_53_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     real
    0.46
    મે
    0.40
    ﺰ
    0.40
     understood
    0.39
    Real
    0.38
     forecasted
    0.38
     energetic
    0.38
    ᖅ
    0.38
     playable
    0.37
    фай
    0.36
    POSITIVE LOGITS
    reality
    0.96
     reality
    0.95
     truth
    0.78
    truth
    0.72
     Reality
    0.72
     حقیقت
    0.71
     Wahrheit
    0.70
    Reality
    0.68
     actuality
    0.65
     réalité
    0.64
    Activations Density 0.003%

    No Known Activations